iwe
Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
No outside reports on file
iwe can access your files and store project information, so you should only use it on code and documents you trust, monitor what it learns, and keep it isolated from sensitive credentials.
Based on public adoption and transparency signals as of Oct 28, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesReads local filesNOTED
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourcenpm (@iwe-org/mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @iwe-org/mcpEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-28.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Iwe
iwe is a tool that helps AI agents and code editors organize and remember information by building a knowledge graph (a structured map of connected facts). It works as both a language server for editors and as a memory system for AI tools, letting you store and retrieve information in a more organized way than plain text.
Who it’s for
Software developers and AI agent builders who want their tools to maintain organized, searchable memory. People using Claude or other AI assistants that benefit from having structured information available.
Alternatives
- Obsidian with local plugins — A note-taking app with graph visualization for knowledge management
- Dendron — A hierarchical note-taking system designed for organizing developer knowledge
- Logseq — An open-source knowledge graph tool similar to Obsidian
- Built-in AI context windows — Many AI tools now let you upload files directly rather than using a memory system
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/iwe-org/iwe (opens external site) for installation and configuration details, as setup may vary based on your editor or AI platform.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.8k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- File system access: Can read and write files on your computer wherever you point it, potentially modifying or leaking project files
- Memory storage: Stores information it learns about your projects; if that storage is accessed, it reveals what you've been working on
- Injection attacks: Markdown or code snippets in your files could contain tricks that confuse the knowledge graph or the AI agent using it
- Editor integration: May execute commands through your editor if misconfigured, potentially running untrusted code
- Data retention: Information stored in the knowledge graph persists; unclear what happens to sensitive data if the tool is compromised
How to lower the risk
Least-privilege permissions
- Only give iwe access to project folders it actually needs
- Don't point it at directories containing passwords or secrets
Network isolation
- Disable any network features if running locally and not needed
- Review what data it sends before connecting to cloud services
Monitoring
- Check what information the knowledge graph stores regularly
- Review file changes it makes to catch unexpected modifications
Red flags to watch for
- Unexpected file deletions or changes in your project
- Memory content that looks corrupted or contains injected code
- Performance drops suggesting background processing of large amounts of data
Questions
How do I install Iwe?
Run npx -y @iwe-org/mcp in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/iwe-org/iwe.
Are there security reports about Iwe?
No reports found for this package in our research (last checked 2026-10-30). Iwe currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include file system access, memory storage, injection attacks.
Is Iwe actively maintained?
Iwe has 1.8k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/iwe-org/iwe before pinning it in production.
What are alternatives to Iwe?
Notable alternatives to Iwe include Obsidian with local plugins (A note-taking app with graph visualization for knowledge management), Dendron (A hierarchical note-taking system designed for organizing developer knowledge), Logseq (An open-source knowledge graph tool similar to Obsidian), Built-in AI context windows (Many AI tools now let you upload files directly rather than using a memory system). You can also compare Iwe side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Iwe? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/iwe-org-iwe)HTML embed:
<a href="https://agentarmorhq.com/skills/iwe-org-iwe"><img src="https://agentarmorhq.com/api/badge/iwe-org-iwe" alt="AgentArmorHQ Risk Grade for Iwe" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "iwe-org-iwe"Share with your security lead
Need sign-off to use iwe? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: iwe
- **Listing URL:** https://agentarmorhq.com/skills/iwe-org-iwe
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.8k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** Reads local files
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** npm (@iwe-org/mcp)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts @iwe-org/mcp`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 28, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- iwe-org
- Source code
- github.com/iwe-org/iwe
- Install command
- npm install @iwe-org/mcp
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 1.8k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-28
Community
Discussions for Iwe
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude